OpenSentience is the research layer of ComputeDriven ? That chip covers nothing, on purpose — the 12 protocols on this page run from one shipped to five drafts, so a single chip would be an average and an average would be a lie. Each protocol card carries its own status. The one artifact that would carry a rung on its own is the κ proof below, which runs in your browser.
Open research into machine cognition

Intelligence isn't generated. It accumulates.

What should a system remember, when should it reconsider, how would it know whether it improved, and what must it never be allowed to do? Those questions are published here as protocols, implementations, experiments and evidence — and this page's own build refuses any claim it has not earned. The book is the way in; the proof below runs in your browser.

12 protocols OS-001 → OS-012 1 shipped · 4 spec-complete · 2 in development · 5 draft
OpenSentience.org Unboxed Patterns Elements of Composable Locus-Oriented Software Read it on the web →

A generator answers. A system accumulates.

The agent ecosystem builds on a frozen model and prays. The limiting factor isn't raw model intelligence — it's memory architecture, deliberation structure, temporal grounding, and governance. Those are infrastructure problems, not parameter problems. Here is the gap, axis by axis.

A generator
A cognitive system
Memory
forgets past the context window
typed graph — nodes, confidence, provenanceOS-001
Evidence
every answer equally certain
weighs evidence across sessions; decaysOS-001
Reasoning
one forward pass, always
routes on topology; deliberates only when κ>0OS-002 · OS-003
Time
stateless; no sense of when
has a heartbeat — declares its own cadenceOS-010 PULSE
World
text in, text out
perceives & acts through a body; learns from surpriseOS-011
Control
deploy and pray
permissions, audit, autonomy; every verdict certifiedOS-006 · box-and-box

What this page is entitled to claim.

Every surface in this portfolio carries the same five rows, and the fourth is the one that costs something to write. The chip in the band above reads ?, and it reads that because it is derived from the twelve protocol statuses rather than chosen — a page with one shipped protocol and five drafts does not get to average itself into a rung.

Status
The κ proof is exhaustive and runs client-side: 1,052,740 directed graphs on 2–5 nodes and 873,611 finite maps on 2–7 nodes, with 0 counterexamples. The governance floor below it is property-tested — 109 kernel laws and 101 compose laws, at 2,000 trials each. Everything else on this page is a specification, and each card says which.
Last verified
2026-08-16
Source
The proof is in /kappa_proof.js and runs in the reader's own browser with no server. The law counts were re-derived on 2026-08-23 by running node test/laws.mjs and node test/compose-laws.mjs against the box-and-box package; both suites derive their own printed totals, and scripts/law-manifest.mjs writes them to LAW_MANIFEST.json, which every published count in the tree is checked against.
Limit
Exhaustive verification of an equivalence over finite structures is not evidence that routing on it helps. κ > 0 ⟺ a nontrivial strongly connected component is a theorem about graphs; that deliberating when κ > 0 produces better answers than not is an empirical claim, and nothing on this page tests it. Nine of the twelve protocols have no implementation at all, and the one benchmark figure quoted here was produced by us, on our own system.
Next rung
external — Someone who is not us runs the κ proof and reports the result, or benchmarks a memory system through PRISM and publishes a number we did not produce. Every figure on this page today has one author.

Three questions, and what would settle each.

A research programme is defined by what would change its mind. Each of these names where it lives in the tree, what is already established, what is not — and the specific result that would move it. The status beside each protocol is read from the protocol record, not written here.

Q1

Can the shape of a knowledge graph tell an agent when to deliberate?

OS-002 spec-complete OS-005 spec-complete

Established. The κ invariant is proved exhaustively — the proof below runs in your browser and finds no counterexample.

Not established. That topology can be measured says nothing about whether routing on it helps. The routing benefit is untested, and it is this page's own stated limit.

What would settle it. One measured task where κ-routing beats both always-retrieve and always-deliberate on the same corpus. OS-005 makes the sharper bet — that the margin inverts on cheap hardware, because topology is most valuable when it tells you to skip an expensive inference entirely.

Q2

Can memory improve continuously without quietly corrupting itself?

OS-001 shipped OS-009 in-development

Established. One system runs the loop and another measures it, end to end.

Not established. The instrument and the subject are both ours. A benchmark we wrote, scoring a system we wrote, is not evidence about either — and PRISM rewrites its own scenarios as systems improve, so if the benchmark optimises against the system it measures, the score stops meaning anything at some point nobody has located.

What would settle it. Someone who is not us, running the benchmark against a system that is not ours. Beneath it a narrower question we can answer in-house: should consolidation fire on surprise (OS-011 emits prediction error into the loop) or on a schedule — and which actually crystallises better knowledge?

Q3

Can autonomous agents coordinate without surrendering accountability?

OS-006 in-development

Established. The governance floor underneath the stack decides one action at a time and ships a certificate with every verdict.

Not established. Coordination as such is not something OpenSentience has. A floor that governs a single decision is not a protocol for many agents holding to it at once, and nothing here has shown that. Printing a question with no work behind it is the point.

What would settle it. A run in which agents with conflicting claims reach a safe outcome with no central arbiter, and every step is auditable afterwards. OS-012 SCOPE sketched typed spatial claims checked pairwise — it is deferred and has no spec file, so it is a sketch, not an answer.

And behind all three, the one this site exists to ask: if a system holds the right relationships at high confidence and can navigate them to answer, does it understand the domain?

We don't ask you to trust the thesis. We ship the receipts.

Every claim here is checkable. The headline κ proof runs exhaustively, in your browser, with no server and no trust required — and it's only one of the receipts.

The κ invariant OS-002 · topology as a cognition signal

DAG region

κ = 0
No circular dependencies. Context is one traversal. Route: fast — no deliberation needed.

SCC region

κ > 0
Irreducible feedback loops. κ measures entanglement depth. Route: deliberate — fault lines become prompt boundaries.

The graph's structure mechanically determines the prompt structure — no human prompt engineering. The topology is the reasoning template. The Deliberator writes conclusions back as new nodes, so κ falls as uncertainty crystallizes into settled knowledge.

Verify it yourself 1,926,351 finite systems · 0 counterexamples

Part 1 — Directed graphs (n=2..5): for all 1,052,740 graphs, verify κ(G) > 0 ⟺ β₁(G) > 0 ⟺ G has a nontrivial strongly connected component.

Part 2 — Finite dynamical systems (n=2..7): for all 873,611 maps f:[n]→[n], verify κ(TransitionGraph(f)) > 0 ⟺ f has a periodic orbit of period > 1.

Part 1: Directed graphs

nGraphsWith SCCsFailuresr(κ, β₁)TimeStatus

Part 2: Finite dynamical systems

nMapsPeriodicFailuresTimeStatus

From theorem to shipping product

The proof verifies the invariant across 1,926,351 mathematical objects. Here is what happens when κ meets a real knowledge graph on a live MCP server.

Step 1

Store a business cycle

4 nodes stored:
  Market Share → Revenue → R&D → Product Quality → Market Share

All edges: causal type
MCP tools used: store_node × 4, then edge creation
Step 2

Analyze topology

routing:        deliberate
max_kappa:      1
scc_count:      1
fault_line:     Product Quality → Market Share
deliberation:   max_iterations: 2, agents: 1, confidence: 0.75
The system identified one strongly connected component over all four nodes, computed κ = 1, and named Product Quality → Market Share as the fault-line edge — the single edge whose removal breaks the loop. This is the first agent memory system to route inference depth on proved graph topology. — Phase 0 validation · 13/13 MCP integration checks passed

The stack, status-aware.

[&] composes agents. PULSE gives them a heartbeat. PRISM measures their effect. They're independent — adopt one without the others — and they stack, mirroring how HTTP, HTML and CSS converged in the browser. Underneath them all sits an un-weakenable governance floor.

Cognition is a loop, not a prompt.

Every system in the [&] portfolio runs the same five-phase loop — the canonical PULSE phase kinds, which are exactly the Graphonomous machine architecture. Each phase is a place where a protocol does its work. The loop is wrapped by governance, clocked by PULSE, gauged by PRISM, and bounded by SCOPE.

The cognition loop drawn as a ring: Retrieve, then Route, then Act, then Learn, then Consolidate, then back to Retrieve. The same phases are listed beside this diagram. ↻ the cognition loop 1 2 3 4 5
  1. 1
    Retrieve pull the relevant subgraph before reasoning OS-001
  2. 2
    Route measure topology (κ) — retrieve in one pass, or deliberate OS-002 · OS-004
  3. 3
    Act deliberate along fault lines, then mutate the graph and the world OS-003 · OS-011
  4. 4
    Learn update confidence from outcomes and prediction-error surprise OS-001 · OS-011
  5. 5
    Consolidate merge, decay, and crystallize at idle — κ falls over time OS-001

Wrapped, clocked, gauged & bounded —

Governed

every phase runs under permissions, audit, and three autonomy levels

OS-006 · OS-007 · OS-008
PULSE · the clock

declares the loop's phases, cadence, and cross-loop signals

OS-010
PRISM · the gauge

measures how well the loop performs over time

OS-009
SCOPE · the bounds

bounds where agents may act over shared space

OS-012

12 protocols. The shape of a mind.

Not a list — a structure. Eight cognitive primitives (OS-001 → OS-008), each one capability of an intelligent system, grounded in cognitive science. Above them, four cross-cutting algebras that measure, time, embody, and bound the whole — the rings around the loop. Range OS-001 → OS-012, every entry honest about its status.

Shipped · 1 Spec complete · 4 In development · 2 Draft · 5

Eight cognitive primitives OS-001 → OS-008 · the capabilities

OS-001 · Continual Learning Protocol

Graphonomous: Knowledge Graphs for Continual Agent Learning

A graph-backed memory engine where agents store episodic, semantic, and procedural knowledge as typed nodes with confidence scores and provenance chains. Multi-timescale consolidation inspired by hippocampal replay — fast memory promotes to slow memory, weak connections decay, strong patterns crystallize. Outcome-driven learning updates confidence across causal chains, not just individual nodes.

v0.4.3 · shipped LongMemEval 92.6% proxy npm v0.4.2 &memory.graph SQLite + embeddings MCP server
OS-002 · Topological Routing Protocol

κ-Routing: When to Retrieve, When to Deliberate

The cyclicity invariant κ (kappa) detects irreducible feedback loops in a knowledge graph. When κ = 0, the subgraph is a DAG — retrieve context in one pass. When κ > 0, circular dependencies exist — iterate and deliberate before answering. κ determines not just whether to think harder, but how entangled the reasoning is. Proved on 1,926,351 finite systems with zero counterexamples. Fault-line edges (minimum cuts within SCCs) become the mechanical decomposition boundaries for deliberation.

spec complete &reason.deliberate Tarjan SCC bipartition enumeration
OS-003 · Deliberation Orchestrator Protocol

Topology-Driven Deliberation: Fault Lines as Prompt Boundaries

When κ > 0, fault-line edges become prompt boundaries. The Deliberator decomposes circular knowledge along those boundaries, runs focused reasoning passes on each partition, reconciles them, and writes conclusions back into the graph — reducing κ over time as uncertainty crystallizes into settled knowledge. Single-agent fast path; escalates to multi-agent formal argumentation (Deliberatic) only when convergence fails.

spec complete &reason.deliberate graph crystallization escalation path
OS-004 · Attention Engine Protocol

Proactive Attention: Self-Directed Cognition Without Queries

The missing ignition in a reactive system. The Attention Engine is a periodic loop that examines the knowledge graph's topology, coverage gaps, and active goals to decide what the system should reason about, learn about, or act on next — without waiting for a query. Three modes: Explore (what don't I know?), Plan (what should I do?), and Focus (where should I spend compute?). Not a 5th cognitive primitive — attention is meta-reasoning over the existing four.

spec complete survey → triage → dispatch heartbeat + event triggers autonomous goal generation
OS-005 · Model Tier Adaptation Protocol

Hardware-Adaptive Cognition: Same Topology, Different Depth

κ routing becomes more valuable on constrained hardware — it tells the system when to skip expensive inference entirely. Three tiers (local 8B, local 70B+, cloud frontier) with qualitatively different strategies: single-pass enrichment vs. multi-pass deliberation, demand-triggered vs. heartbeat attention, aggressive crystallization vs. fresh inference. The κ paradox: ROI of topological routing is highest when inference is most expensive.

spec complete local_small · local_large · cloud_frontier cost tracking
OS-006 · Agent Governance Shim Protocol

Thin Governance: Permissions, Audit, and Lifecycle for Any Runtime

A lightweight governance layer — not a full runtime — that wraps around any OTP-based agent system (Jido, Alloy, or raw GenServer). Provides the permission taxonomy (filesystem, network, tool invocation, graph access), audit trail, agent lifecycle states (installed → enabled → running), and three autonomy levels (observe, advise, act). Designed as a hex package dependency, not a daemon.

in development permissions model audit trail autonomy levels
OS-007 · Adversarial Robustness Protocol

Pattern Recognition and Threat Defense

Defines how agent systems detect and defend against adversarial inputs, compromised agents, and knowledge poisoning. Five threat categories: prompt injection, knowledge poisoning (BadRAG/TrojanRAG), agent impersonation, privilege escalation, and denial of service.

draft &govern.identity Immune system — self/non-self discrimination
OS-008 · Agent Harness Protocol

Pipeline Enforcement and Quality Gates

The enforcement runtime that sits above agents and below humans. Orchestrates [&] pipelines, enforces governance contracts, gates execution on epistemic confidence. Five components: PipelineEnforcer, QualityGate, ContractValidator, SprintController, ContextManager.

draft &govern.harness Supervisory attentional system — Norman & Shallice (1986)

Four cross-cutting algebras OS-009 → OS-012 · the rings

Grounded in cognitive science, not analogy

&
&memory → hippocampus + neocortex

Tulving's episodic/semantic split; multi-store memory; hippocampal–neocortical replay. Graphonomous consolidates fast→slow on idle.

&
&reason → prefrontal cortex

Kahneman's dual-process theory. κ-routing implements the System-1/System-2 split mechanically, from graph topology alone.

&
&time → cerebellum + basal ganglia

Temporal-difference learning; sequence timing. PULSE gives every loop a declared cadence and cross-loop signals.

&
&space → entorhinal grid cells

O'Keefe & Nadel's cognitive-map theory; place & grid cells. SCOPE is an N-D region algebra for shared-space coordination.

PRISM
diagnostic
measures how well a loop performs over time
in development
PULSE
temporal
declares how loops cycle, nest and signal
draft
Embodiment
sensorimotor
the typed perceive/act loop for &body.*
draft
SCOPE
spatial
deferred 2026-06-12 — no spec file exists, and its prerequisites are unmet
draft
OS-001 … OS-008
capability
the eight cognitive primitives
1 shipped4 spec-complete1 in development2 draft
[&]
structural
composes capabilities into agents
no rung on this ladder
box-and-box
governance floor
decides what is allowed, and what is best
no rung on this ladder
What connects them, and what has actually been run
PRISM reads a system's PULSE manifest to discover its phases available, unverified produced by the PULSE loop-manifest schema · consumed by PRISM's dual-loop machine spec
each product declares its loop topology as a PULSE manifest available, unverified produced by the reference manifests · consumed by Graphonomous's spec, which carries a PULSE Loop Manifest section
capabilities compose into agents available, unverified produced by the protocol specs · consumed by the [&] protocol docs
every verdict passes the governance floor available, unverified produced by the [&] reference implementation · consumed by the derived law manifest
OS-011 emits a SurpriseSignal into the loop vocabulary endpoint absent produced by the Embodiment spec · no consumer — no implementation consumes it. The SurpriseSignal token exists in PULSE v0.1.1 and nothing emits one, so this end is absent.
OS-012 would carry spatial claims into the loop vocabulary endpoint absent no producer — there is no SCOPE spec file anywhere in the tree — the 'v0.1 draft' is a design reviewed in prose in a planning doc and never committed · no consumer — Graphonomous has no `region` field and there is no region-scoped consumer, which is why OS-012 was deferred on 2026-06-12
integration has runan executable test or a generated receipt names and exercises both endpoints, and it passed
available, unverifiedboth endpoints exist and nothing has exercised the connection between them
endpoint absentone or both endpoints do not exist

The governance floor box-and-box · 109 kernel laws × 2000 trials

Protocols say what a system can do. box-and-box answers the question underneath them all: given everything it could do, what is it allowed to do, and which option is best? An eight-rung modality ladder, each rung a small algebra with stated laws, composed by one bridge that runs feasible ▸ permitted ▸ best over a safety floor that cannot be weakened. Every verdict ships a certificate.

Two counts, two scopes — and they are not a discrepancy. node test/laws.mjs enforces the 109 kernel laws — the eight rungs and their bridges — which is the suite this page and the playground refer to. node test/compose-laws.mjs enforces a further 101 compose/CC2 laws (the & and |> brick operators; 14 in the suite plus the AC-COMM anchor), for 210 enforced in total — the number ampersandboxdesign.com quotes. It also declares 3 open gaps (CP5/CP6/CP7, the Value.pi carrier) which print FALSIFIED in red by design; the build fails if one starts passing. Counts measured by running both suites on 2026-08-24, at 2,000 trials per law. Nothing here is fetched at runtime — re-run the suites to check us.

The catalog as evidence.

Unboxed Patterns is a generated registry: every entry carries the rung its evidence has earned, and the build refuses an entry whose witness does not check out. It is the source material the book is written from — a catalogue and an editorial narrative serve different readers, and today they are the same object. When an edition is written it gets its own record, and the invitation above changes by itself, because nobody types it.

32 entries 15 carry a witness rung 0 reproduced by someone else

That third number is the one that matters and it is the one that is hard to move. Everything else on this page is us checking our own work.

Open the catalog
The cover of Unboxed Patterns: one mark for each of its 32 chapters, 2 deployed, 13 in the tree, 1 written down, 16 no witness yet. Read on the web; there is no file to download.
  • 2 deployed
  • 13 in the tree
  • 1 written down
  • 16 no witness yet

One mark per chapter, coloured by the rung its evidence has earned — a filled mark is witnessed, an empty ring is not. Nothing here was drawn by hand. The book is read on the web; there is no file.

Three rungs, three different invitations.

A page may only ask you to do what its evidence has earned. The κ proof is deployed and runs on your machine, so it asks you to run it. The governance floor is written and property-tested, so it asks you to run the suites and read the source. The rest is a specification, so it can ask you to read it, argue with it or implement it — and never to run something that does not exist. The verbs below are not chosen; they are the ones each rung allows, and the build refuses any other.

Or come in as a researcher, a builder, a skeptic

Researcher

Read the specs and the cognitive-science grounding behind every protocol. Twelve numbered specs, full reference lists, no marketing.

Builder

Wire the loop into your own agent. Graphonomous is the shipped memory engine (npm + MCP); the governance shim is a hex package that wraps any OTP tree.

Start a Graphonomous session for this repo.
1. retrieve(action:"context", query:"session context")
2. route(action:"attention_survey")
Then work, storing durable knowledge as we go.

Skeptic

Don't trust us — run it. The κ proof is right above. Or point PRISM at your own repo (BYOR) and benchmark any memory system, including ours, end to end.

config(action:"register_system", name:"graphonomous")
compose(action:"byor_register", repo_url:".")
compose(action:"scenarios") → interact(action:"run")
observe(action:"judge_transcript") → reflect("analyze_gaps")

Or tell us we have a number wrong

This page prints an exhaustive proof, two law counts and twelve protocol statuses, and every one of them has a single author — us. The most useful message this site can receive is the one that says a figure on it does not hold. The form posts to formspree.io when you press the button, carrying what you typed and nothing else; it is the only thing on this page that talks to anyone but this domain. If you would rather the correction be public, open an issue instead.

Standing on the work of others.

Cognitive Architectures

Memory & Neuroscience

Agent Protocols & Deliberation

Modal Logic, Decision Theory & Measurement

Industry & Surveys